Temporal Continual Learning with Prior Compensation for Human Motion Prediction

• URL: http://arxiv.org/abs/2507.04060v1
• Date: Sat, 05 Jul 2025 14:48:30 GMT
• Title: Temporal Continual Learning with Prior Compensation for Human Motion Prediction
• Authors: Jianwei Tang, Jiangxin Sun, Xiaotong Lin, Lifang Zhang, Wei-Shi Zheng, Jian-Fang Hu,
• Abstract summary: Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences.<n>Previous approaches have treated the prediction of various moments equally, resulting in two main limitations.<n>We introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges.
• Score: 32.764096325603994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning of short-term predictions is hindered by the focus on long-term predictions, and the incorporation of prior information from past predictions into subsequent predictions is limited. In this paper, we introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges. To better preserve prior information, we introduce the Prior Compensation Factor (PCF). We incorporate it into the model training to compensate for the lost prior information. Furthermore, we derive a more reasonable optimization objective through theoretical derivation. It is important to note that our TCL framework can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on four HMP benchmark datasets demonstrate the effectiveness and flexibility of TCL. The code is available at https://github.com/hyqlat/TCL.

Related papers

• Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs? [32.04523360747506]
  We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations.<n>We introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%.
  arXiv  Detail & Related papers  (2025-04-16T21:19:09Z)
• Annealed Winner-Takes-All for Motion Forecasting [48.200282332176094]
  We show how an aWTA loss can be integrated with state-of-the-art motion forecasting models to enhance their performance.<n>Our approach can be easily incorporated into any trajectory prediction model normally trained using WTA.
  arXiv  Detail & Related papers  (2024-09-17T13:26:17Z)
• Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting [11.96384267146423]
  We propose to directly predict the causes via time series forecasting (TSF) of clinical variables. Because model training does not rely on a particular label anymore, the forecasted data can be used to predict any consensus-based label.
  arXiv  Detail & Related papers  (2024-08-07T14:52:06Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• Loss Shaping Constraints for Long-Term Time Series Forecasting [79.3533114027664]
  We present a Constrained Learning approach for long-term time series forecasting that respects a user-defined upper bound on the loss at each time-step. We propose a practical Primal-Dual algorithm to tackle it, and aims to demonstrate that it exhibits competitive average performance in time series benchmarks, while shaping the errors across the predicted window.
  arXiv  Detail & Related papers  (2024-02-14T18:20:44Z)
• Examining the Effect of Pre-training on Time Series Classification [21.38211396933795]
  This study investigates the impact of pre-training followed by fine-tuning on the fine-tuning process. We conducted a thorough examination of 150 classification datasets. We find that pre-training can only help improve the optimization process for models that fit the data poorly. Adding more pre-training data does not improve generalization, but it can strengthen the advantage of pre-training on the original data volume.
  arXiv  Detail & Related papers  (2023-09-11T06:26:57Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)
• Prediction-Oriented Bayesian Active Learning [51.426960808684655]
  Expected predictive information gain (EPIG) is an acquisition function that measures information gain in the space of predictions rather than parameters. EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models.
  arXiv  Detail & Related papers  (2023-04-17T10:59:57Z)
• Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment [72.50906475214457]
  The goal of sequential event prediction is to estimate the next event based on a sequence of historical events. In practice, the next-event prediction models are trained with sequential data collected at one time. We propose a framework with hierarchical branching structures for learning context-specific representations.
  arXiv  Detail & Related papers  (2022-10-24T07:54:13Z)
• Probabilistic prediction of the heave motions of a semi-submersible by a deep learning problem model [4.903969235471705]
  We extend a deep learning (DL) model to predict the heave and surge motions of a floating semi-submersible 20 to 50 seconds ahead with good accuracy. This study extends the understanding of the DL model to predict the wave excited motions of an offshore platform.
  arXiv  Detail & Related papers  (2021-10-09T06:26:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.